alt Hacker NewsI saw a (highly reputable of course) tweet a few days back suggesting all of OpenRouter's DS4 traffic would fit on a single rack of modern Nvidia kit.
I saw a (highly reputable of course) tweet a few days back suggesting all of OpenRouter's DS4 traffic would fit on a single rack of modern Nvidia kit.
Hm, that’s doubtful. I think even one instance of DS 4.1 Flash alone at ~500B parameters needs a full node (8 GPUs).